Multi-layered tree crown extraction from LiDAR data using graph-based segmentation

doi:10.1016/j.compag.2020.105213

Return

Multi-layered tree crown extraction from LiDAR data using graph-based segmentation

2020-03-01

PRE

Tianyang Dong

Xinpeng Zhang

Jing Fan *

DOI：10.1016/j.compag.2020.105213

Original

Original request for help

Save

Abstract

En 中文

With the development of Light Detection and Ranging (LiDAR) and Unmanned Aerial Vehicle (UAV) technology, extracting tree crowns from LiDAR data and infering their geometrical features are becoming more available for everyone. Although the forest has a significant stratification phenomenon in the vertical direction, the existing individual tree detection methods generally aimed at solving overstory trees detection. As a result, the understory trees cannot be effectively extracted. To effectively detect individual tree from multi-layer forests, a multi-layered tree extraction method using a graph-based segmentation algorithm was proposed in this study. First, using the graph-based segmentation algorithm delineates the canopy of the overstory tree on the canopy height model (CHM) generated by LiDAR data. Then, using the sliding window detection method extracts the LiDAR data of understory trees. Finally, the information of understory trees is extracted by the graph-based segmentation algorithm. To verify the performance of the proposed method, this study selected six experimental plots from two research areas. According to the result of our method, the highest matching score and average score for overstory trees reached 91.3 and 86.3; the highest matching score and average score for understory trees reached 78.1 and 63.2. Compared with other methods, our method has better detection results. The experimental results show that the proposed method can extract the understory and overstory trees effectively, thus improving the accuracy of individual tree extraction in multi-layered forests.

Keywords:

LiDAR

Individual tree detection

Graph-based segmentation

Tree structure

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.